{"list":"other","total":75,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425},{"id":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2106.14413","title":"Co$^2$L: Contrastive Continual Learning","created":"2021-06-28","cited_by_count":244},{"id":"2312.03031","title":"Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?","created":"2023-12-05","cited_by_count":242},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"1810.12488","title":"Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines","created":"2018-10-30","cited_by_count":228},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"2412.14169","title":"Autoregressive Video Generation without Vector Quantization","created":"2024-12-18","cited_by_count":186},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154},{"id":"2112.04215","title":"Self-Supervised Models are Continual Learners","created":"2021-12-08","cited_by_count":149},{"id":"2103.07113","title":"Training Networks in Null Space of Feature Covariance for Continual Learning","created":"2021-03-12","cited_by_count":143},{"id":"2402.04324","title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","created":"2024-02-06","cited_by_count":132},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"2004.05214","title":"A Review on Deep Learning Techniques for Video Prediction","created":"2020-04-10","cited_by_count":114},{"id":"2408.00415","title":"DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving","created":"2024-08-01","cited_by_count":98},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96},{"id":"2110.06976","title":"Representational Continuity for Unsupervised Continual Learning","created":"2021-10-13","cited_by_count":95},{"id":"2312.02934","title":"WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation","created":"2023-12-05","cited_by_count":93},{"id":"2412.15208","title":"OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving","created":"2024-12-19","cited_by_count":93},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2312.04557","title":"GenTron: Diffusion Transformers for Image and Video Generation","created":"2023-12-07","cited_by_count":82},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78},{"id":"2404.07762","title":"NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving","created":"2024-04-11","cited_by_count":62},{"id":"2406.16437","title":"Theory on Mixture-of-Experts in Continual Learning","created":"2024-06-24","cited_by_count":54},{"id":"2409.12753","title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","created":"2024-09-19","cited_by_count":53},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51},{"id":"2406.04277","title":"VideoTetris: Towards Compositional Text-to-Video Generation","created":"2024-06-06","cited_by_count":51},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44},{"id":"2405.14124","title":"Mixture of Experts Meets Prompt-Based Continual Learning","created":"2024-05-23","cited_by_count":43},{"id":"2312.13834","title":"Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis","created":"2023-12-20","cited_by_count":39},{"id":"2403.03077","title":"MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding","created":"2024-03-05","cited_by_count":29},{"id":"1807.09951","title":"Learning to Forecast and Refine Residual Motion for Image-to-Video Generation","created":"2018-07-26","cited_by_count":27},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21},{"id":"2403.16092","title":"Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap","created":"2024-03-24","cited_by_count":20},{"id":"2412.06613","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","created":"2024-12-09","cited_by_count":5}],"next_cursor":null}